Distributed Systems Engineer

About the role

We are building the runtime and registry for AI/LLM tools. You will define both how AI interacts with the world, and how humans build and manage those tools. This includes creating production-grade integrations, and the services & toolkits that run them... and the solving the unique problems of AI/LLM usage along the way.

Responsibilities

• Build the infrastructure to manage the backplane for all future AI tools
• Design, build, test, and deploy high-performance, secure, production-grade software
• Develop SDKs and frameworks that make it easy for other developers to build custom tools
• Help set industry standards for tool calling and authorization (for example, we helped write the MCP authorization spec)
• Create integrations with major platforms and LLMs (Google Workspace, Microsoft 365, OpenAi, Anthropic, etc.)
• Shape the roadmap for the team
• Build leverage (via AI) - projects that take a week today should take a day next time

Requirements

• An insatiable desire to ship
• 7+ years of software engineering experience comprising of: 5+ years of backend development experience with either Python, Go, Ruby, Typescript, or a similar language and API & Web frameworks
• 2+ years of experience with infrastructure and deployment (AWS/GCP, Terraform, Helm, etc)
• Strong experience building and maintaining production APIs
• Track record of writing clean, well-documented, well-tested code
• User-centered approach to designing developer-centric products and tools

Qualifications

• Experience building developer tools or SDKs
• Familiarity with LLMs and AI frameworks (Langchain, LlamaIndex, etc)
• Open-source contributions
• Experience with high-scale distributed systems
• Experience leading teams and mentoring more junior developers
• Familiarity with Typescript and a relevant frontend framework (e.g. React)

Skills

• Experience with Go, Python, or Typescript

Benefits

• Inspiring mission: Transforming AI from just chatbots to agents that can take actions against real systems
• Collaborative environment: Working with a dream team of experts from Okta, Redis, Microsoft, Splunk, Ngrok, Google, Airbyte, Disney, and HPE
• Exciting growth: Building critical infrastructure for the biggest technological shift of our generation

Pay

• $150k - $200k base salary

Schedule

• Full-time, in-person role located in our San Francisco (SOMA) office